CSI8755-01 Topics in Fuzzy Systems: Life Log Management

1
CSI8755-01Topics in Fuzzy SystemsLife Log
Management

• Fall Semester, 2008

2
Teaching Staffs

• Professor Cho, Sung-Bae
• (C515 ? 2123-2720 sbcho_at_cs.yonsei.ac.kr)
• Web page http//sclab.yonsei.ac.kr/courses/08FuSy
  s
• Class hours
• Tue 2, Thu 3, 4 (A542)
• Office hours
• Tue 5, 6 (C515)
• TA Hwang, Keum-Sung
• (? 2123-4803 yellowg_at_sclab.yonsei.ac.kr)

3
Uncertainties in Intelligent Systems

• Dealing with uncertain and imprecise information
  has been one of the major issues in almost all
  intelligent system
• Decision making systems, diagnostic systems,
  intelligent agent systems, planning systems, data
  mining, etc
• Various approaches to cope with uncertain,
  imprecise, vague, and even inconsistent
  information
• Bayesian and probabilistic methods, belief
  networks, softcomputing, etc
• Softcomputing
• Neural networks, fuzzy theory, approximate
  reasoning, derivative-free optimization methods
  (GA), etc
• Synergy allows SC to incorporate human knowledge
  effectively, deal with imprecision and
  uncertainty, and learn to adapt to unknown or
  changing environments for better performance ?
  intelligent systems to mimic human intelligence
  in thinking, learning, reasoning, etc

4
Life Log
MS SenseCam MyLifeBits
Tokyo University (Aizawa)
5
Life Blog
Nokia Lifeblog
Queens Univ., eyeBlog
6
Life Log Related Works

• Microsoft Research, MyLifeBits
• Microsoft Research, MemoryLens (PhotoViewer,
  LifeBrowser)
• Microsoft Research, JamBayes
• Nokia, LifeBlog
• Helsinki University, ContextPhone
• Carnegie Mellon University, Context-Aware Phone
• MIT Ambient Intelligence Group, PhotoWhere
• MIT Reality Mining Group, Serendipity Service
• MIT Reality Mining Group, Interactive
  automatically generated diary

7
Key Issues
8
Course Objectives

• Introduce the several techniques on fuzzy systems
  pattern recognition, and case studies on recent
  applications for the management of life log
• Cover the themes to manage life log
• Log collection
• Preprocessing
• Recognition and inference
• Application services
• Acquire relevant knowledge through course projects

9
Syllabus

1. 9/2, 4 Course Introduction Overview of Life
   Logging
2. 9/9, 11 Sensor Data Collection
3. 9/16, 18 Preprocessing
4. 9/23, 25 Feature Extraction
5. 9/30, 10/2 Classification
6. 10/7, 9 Bayesian Networks
7. 10/14, 16 Term Project Proposal
8. 10/21, 23 Midterm Exam
9. 10/28, 30 Dynamic Bayesian Networks
10. 11/4, 6 Dynamic Bayesian Networks (SL-1)
11. 11/11, 13 Hidden Markov Models
12. 11/18, 20 Ontology and Context Modeling (SL-2)
13. 11/25, 27 Emotion/Activity Recognition (SL-3)
14. 12/2, 4 Lifelog Management and Visualization
15. 12/9, 11 Term Project Final Presentation
16. 12/16, 18 Final Exam (TBD)

10
Evaluation Criteria

• Evaluation Criteria
• Term Project (written report oral
  presentation) 50
• Written Exam 30
• Presentation 20
• Term Project (Oral presentation is required)
• Theoretical Issue (analysis, experiment,
  simulation) Originality
• Interesting Programming (Game, Demo, etc)
  Performance
• Survey Completeness